Industry Classification

🚀 Industry Classification

A DistilBERT model that classifies business descriptions into 62 industry tags, trained on Indian company data.

🚀 Quick Start

This is a DistilBERT model designed to classify business descriptions into one of 62 industry tags. It was trained on 7000 samples of business descriptions and associated labels of companies in India.

✨ Features

• Multi - class Classification: Capable of classifying business descriptions into 62 different industry tags.
• Cross - framework Support: Available in both PyTorch and TensorFlow.

📦 Installation

No specific installation steps are provided in the original document. However, to use the model, you need to have the transformers library installed. You can install it using the following command:

pip install transformers

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline

tokenizer = AutoTokenizer.from_pretrained("sampathkethineedi/industry-classification")  
model = AutoModelForSequenceClassification.from_pretrained("sampathkethineedi/industry-classification")

industry_tags = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)
industry_tags("Stellar Capital Services Limited is an India-based non-banking financial company ... loan against property, management consultancy, personal loans and unsecured loans.")

'''Output'''
[{'label': 'Consumer Finance', 'score': 0.9841355681419373}]

🔧 Technical Details

The model is based on DistilBERT and is trained on 7000 samples of business descriptions and associated labels of companies in India. It is designed for multi - class text classification tasks, specifically classifying business descriptions into one of 62 industry tags.

📄 License

This project is licensed under the MIT license.